Intelligent digital tools for screening of brain connectivity and dementia risk estimation in people affected by mild cognitive impairment: the AI-Mind clinical study protocol

More than 10 million Europeans show signs of mild cognitive impairment (MCI), a transitional stage between normal brain aging and dementia stage memory disorder. The path MCI takes can be divergent; while some maintain stability or even revert to cognitive norms, alarmingly, up to half of the cases progress to dementia within 5 years. Current diagnostic practice lacks the necessary screening tools to identify those at risk of progression. The European patient experience often involves a long journey from the initial signs of MCI to the eventual diagnosis of dementia. The trajectory is far from ideal. Here, we introduce the AI-Mind project, a pioneering initiative with an innovative approach to early risk assessment through the implementation of advanced artificial intelligence (AI) on multimodal data. The cutting-edge AI-based tools developed in the project aim not only to accelerate the diagnostic process but also to deliver highly accurate predictions regarding an individual's risk of developing dementia when prevention and intervention may still be possible. AI-Mind is a European Research and Innovation Action (RIA H2020-SC1-BHC-06-2020, No. 964220) financed between 2021 and 2026. First, the AI-Mind Connector identifies dysfunctional brain networks based on high-density magneto- and electroencephalography (M/EEG) recordings. Second, the AI-Mind Predictor predicts dementia risk using data from the Connector, enriched with computerized cognitive tests, genetic and protein biomarkers, as well as sociodemographic and clinical variables. AI-Mind is integrated within a network of major European initiatives, including The Virtual Brain, The Virtual Epileptic Patient, and EBRAINS AISBL service for sensitive data, HealthDataCloud, where big patient data are generated for advancing digital and virtual twin technology development. AI-Mind's innovation lies not only in its early prediction of dementia risk, but it also enables a virtual laboratory scenario for hypothesis-driven personalized intervention research. This article introduces the background of the AI-Mind project and its clinical study protocol, setting the stage for future scientific contributions.

Functional, Clinical, and Sociodemographic Variables Associated with Risk of In-Hospital Mortality by COVID-19 in People over 80 Years Old

OBJECTIVES

The objective is to assess the role of functional, clinical, and analytic parameters in predicting mortality in older patients hospitalized due to COVID-19.

DESIGN

Cohort study with a mean follow-up of 12.8 days.

SETTING

Public university hospital (Madrid, Spain).

PARTICIPANTS

499 patients 80 and above consecutively admitted to a Spanish public university hospital between 4 March 2020 and 16 May 2020.

MEASUREMENTS

Mortality was the main outcome. Data of sociodemographic variables (age, sex, living), comorbidities, polypharmacy, functional status, date of hospital admission and length of stay was recorded. Clinical symptoms, laboratory and X-ray findings were collected at time of admission. For multivariant analysis, logistic regressions were performed to identify risk factors for death.

RESULTS

Mean age was 86.7±4.4 with 37% of death. Mortality was associated with male gender [odds ratio (OR) 1.50; 95% confidence interval (CI) 1.01-2.24], with a 5-points increase on Barthel Index [OR 1.01 (95%CI 1.00-1.02)], higher Charlson Index score [OR 1.13 (95%CI 1.02-1.26)] and comorbidities [OR 1.28 (95%CI 1.06-1.53)], hyperpolipharmacy [OR 2.00 (95%CI 1.04-3.82)], unilateral pneumonia [OR 1.83 (95%CI 1.01-3.30)], higher levels of C-reactive protein [OR 1.09 (95%CI 1.06-1.12)] and creatine [OR 1.48 (95%CI 1.15-1.89)]. Higher oxygen levels were a protective factor [OR 0.92 (95%CI 0.89-0.95)].

CONCLUSIONS

Functional status, being male, a higher burden of comorbidities, hyperpolipharmacy, unilateral pneumonia and some laboratory parameters predict in-hospital mortality in this older population. The knowledge of these mortality risk factors should be used to improve the survival of older hospitalized patients.

[Breakthrough cancer pain in the elderly]

Breakthrough pain is defined as an acute exacerbation of pain with rapid onset, short duration and moderate or high intensity, which occurs spontaneously or in connection with a predictable or unpredictable event despite there being stabilised and controlled baseline pain. However, there are doubts about the definition, terminology, epidemiology, and assessment of breakthrough pain, with no clear answers or consensus, especially in the elderly population. This non-systematic review summarises the most important aspects of breakthrough pain in the elderly, based on the limited publications there are in that population group.

[Clinical profile and 90-day mortality in centenarian patients attended in emergency departments]

OBJECTIVES

To determine the clinical profile and to develop a model to predict 90-day mortality in centenarian patients attended in emergency departments (ED).

METHODOLOGY

This was an observational, retrospective, multicentre cohort study including patients >99years attended in 5 ED in the Community of Madrid from January to December 2012. Demographic variables were recorded, as well as, comorbidities, cognitive, functional, social basal status, geriatric syndromes, acute episode, and hospital and social resources use, and 90-day mortality.

RESULTS

The study included 209patients aged 101years (SD 1.7) of whom 161 (77.0%) were female. Sixty four (32.5%) had severe comorbidity (Charlson index≥3), 101 (49.8%) on multiple medication, 100 (52.6%) had cognitive impairment, 82 (42.3%) had severe functional dependence, 85 (40.7%) were institutionalised, and 190 (94.5%) had a geriatric syndrome. Dyspnoea (26.8%), followed by falls (12.4%) were the most common causes of attendance. One hundred and eighteen (56.5%) were admitted, and 58 out of 174 (33.3%) died in the first 90days. The model to predict 90-day overall mortality included male sex (OR 2.42 95% CI=0.97-6.04; P=.059), emergency care in the previous 3months (OR 4.08 95% CI=1.26-13.16; P=.019) and the hospitalization by index event (OR 8.63 95% CI=3.25-22.9; P<.001) and this model had an area under ROC curve of 0.776 (95% CI=0.70-0.85; P<.001).

CONCLUSIONS

Centenarian patients attended in ED had a significant frailty and one in three cases died in the first 90days after being attended, and this was associated with male sex, emergency care in the previous 3months, and hospitalisation.

Brain microbleeds: Epidemiology and clinical implications

INTRODUCTION

Brain microbleeds (BMB) are haemosiderin deposits contained within macrophages, which are displayed as hypointense images in some T2-weighted magnetic resonance imaging sequences. There are still many questions to be answered about the pathophysiology and clinical relevance of BMB.

DEVELOPMENT

We conducted a literature review of the main epidemiological, clinical, and anatomical pathology studies of BMB performed in the general population, in patients at risk of or already suffering from a vascular disease, and in patients with cognitive impairment. We analysed the prevalence of BMB, risk factors, and potential pathophysiological mechanisms and clinical implications.

CONCLUSIONS

The prevalence of BMB is highly variable (3%-27% in the general population, 6%-80% in patients with vascular risk factors or vascular disease, and 16%-45% in patients with cognitive impairment). BMB are associated with ageing, Alzheimer disease (AD), and in particular haemorrhagic or ischaemic cerebrovascular disease. The pathological substrate of BMB is either lipohyalinosis (subcortical BMB) or cerebral amyloid angiopathy (lobar BMB). BMB exacerbate cognitive impairment, possibly through cortical-subcortical and intracortical disconnection, and increase the risk of death, mostly due to vascular causes. BMB also increase the risk of cerebral haemorrhage, particularly in patients with multiple lobar BMB (probable erebral amyloid angiopathy). Therefore, anticoagulant treatment may be contraindicated in these patients. In patients with lower risk of bleeding, the new oral anticoagulants and the combination of clinical and magnetic resonance imaging follow-up could be helpful in the decision-making process.

[Update on oncological pain in the elderly]

Pain is a prevalent symptom in cancer geriatric patients, appearing in up to 90% of patients with terminal cancer. This requires a multidimensional approach, as there is a high percentage of inappropriate assessments and treatments. Unrecognized or poorly treated pain in the geriatric population, especially in cancer patients, leads to the development of disabling symptoms such as depression, anxiety, isolation, sleep disturbances, and appetite, and very especially, loss of functional capacity and quality of life. In this review an analysis is made on the most relevant studies on the diagnosis and management of cancer pain in the geriatric population.

MEG delta mapping along the healthy aging-Alzheimer's disease continuum: diagnostic implications

New diagnostic criteria for Alzheimer's disease (AD) stress the role of in vivo biomarkers. Neurophysiological markers are usually not considered as such criteria, although theoretical and practical reasons would justify them. In order to assess the value of neurophysiology as an AD biomarker, whole-head magnetoencephalographic (MEG) resting state recordings were obtained from 35 AD patients, 23 mild cognitive impairment (MCI) patients, and 24 healthy controls. The AD group was further split into two groups differing in severity according to the GDS/FAST criteria. A Minimum Norm Estimation procedure was utilized to estimate the cortical origin of slow brain oscillatory activity in the delta band (2-4 Hz). Eight regions of interest (ROIs) discriminated between AD patients and controls. Delta current density (DCD) in all ROIs showed a significant negative correlation with cognitive status (p < 0.001). DCD values in posterior parietal, occipital, prerolandic, and precuneus cortices distinguished reliably between MCI patients, AD patients with different severity scores, and controls. Importantly, an increase of DCD in right parietal cortex and precuneus indexed the transition from MCI to mild dementia and from mild to more severe dementia. MEG delta mapping might be a serious candidate for a "neural degeneration" marker of AD reflecting dysfunctional synaptic transmission. More importantly, the localization of DCD values is in line with functional imaging markers of AD. However, MEG delta mapping is a totally non-invasive technique that directly measures neural activity. We propose that individuals with enhanced DCD in posterior parietal and precuneus cortices are at risk of progression to full dementia.

Brain activity patterns in stable and progressive mild cognitive impairment during working memory as evidenced by magnetoencephalography

It has been reported that mild cognitive impairment (MCI) patients, when compared with controls, show increased activity in different brain regions within the ventral pathway during memory tasks. A key question is whether this profile of increased activity could be useful to predict which patients will develop dementia. Herein, we present profiles of brain magnetic activity during a memory task recorded with magnetoencephalography from MCI patients (N = 10), Alzheimer's disease (AD) patients (N = 10), and healthy volunteers (N = 17). After 2½ years of follow-up, five of the MCI patients developed AD. Patients who progressed to AD (PMCI) showed higher activity than those who remained stable (SMCI), AD patients and controls. This increased activity in PMCI patients involves regions within the ventral and dorsal pathways. In contrast, SMCI patients showed higher activation than controls only along the ventral pathway. This increase in both the ventral and dorsal pathways in PMCI patients may reflect a compensatory mechanism for the loss in efficiency in memory networks, which would be absent in AD patients as they showed lower activity levels than the rest of the groups.

MEG spectral profile in Alzheimer's disease and mild cognitive impairment

OBJECTIVE

In this study, we applied a novel procedure to calculate the mean frequency from the Magnetoencephalography (MEG) signals of 22 patients with Alzheimer's Disease (AD), 22 patients with mild cognitive impairment (MCI), and 21 healthy controls. A significant mean frequency decrease was expected in pathological groups. MCI subjects are expected to show intermediate mean frequency values between AD patients and controls.

METHODS

MEG signal was obtained from a whole-head 148 channels magnetometer in a resting condition. We estimated the power spectral density from the MEG signal by means of the Fourier transform of the autocorrelation function. Then, we computed the mean frequency for each subject.

RESULTS

Mean frequency was higher in controls (12.46 +/- 2.00 Hz, mean +/- SD) than in MCI subjects (10.82 +/- 2.21 Hz) with significant differences (P < 0.05). Moreover, mean frequency values in MCI subjects were higher than in AD patients (9.06 +/- 2.48 Hz, P < 0.05). We also detected a decrease of 0.17 Hz per year in mean frequency from normal subjects' MEG (P < 0.05)

CONCLUSIONS

Results demonstrated that the approach adopted for the calculation of a mean frequency score seems to be adequate and sensitive to detect differences between normal aging, cognitive deterioration and AD. In addition, data may contribute to the theoretical discussion on the nature of mild cognitive impairment and its similitudes with Alzheimer's disease.

SIGNIFICANCE

This paper may be considered a first step to obtain a reliable measure which summarizes spectral information, and might be of a potential clinical interest.

Medial temporal lobe neuromagnetic hypoactivation and risk for developing cognitive decline in elderly population: A 2-year follow-up study

Cognition declines as a function of age. However, some elders could develop more severe status such as mild cognitive impairment (MCI). The aim of this study was the early detection of neurophysiological patterns of brain activity that may predict the possibility of certain subjects to develop MCI. Brain magnetic activity was recorded from 15 healthy subjects during a memory task by means of magnetoencephalography. None of the participants could be considered as MCI at the time of the first clinical evaluation. After 2-year follow-up, five subjects developed MCI and 10 maintained their cognitive status across time. The subjects who developed cognitive decline showed a lower number of activity sources in the left medial temporal lobe between 400 and 800 ms after stimulus onset, as compared to the non-cognitive decline group. These findings may help with the early identification of elderly subjects at high risk of cognitive decline, allowing the possibility of neuropsychological or pharmaceutical treatment that delay or prevent the progression of the cognitive impairment.

Evidence of biochemical and biomagnetic interactions in Alzheimer's disease: an MEG and MR spectroscopy study

BACKGROUND

Several neuroimaging studies have shown reliable differences between Alzheimer's disease (AD) patients and age-matched controls. However, few studies have demonstrated the interactions between neuroimaging methods for the diagnoses of AD.

OBJECTIVE

In this study, we try to elucidate the complementary nature of magnetoencephalography (MEG) and magnetic resonance spectroscopy (MRS) examinations in the assessmentof AD.

METHODS

Ten patients fulfilling the NINCDS-ADRDA criteria of probable AD, and 10 elderly individuals with no history of neurological or psychiatric illness serving as age-matched controls participated in the study. All patients and controls received an MRS, MEG and neuropsychological assessment. MEG data were obtained in the context of a working memory task, previously utilized in a similar sample of patients.

RESULTS

The AD group showed a reduced number of activity sources over left temporoparietal areas during the late portion of the evoked magnetic field (between 400-800 ms), as well as a bilateral temporoparietal increase in creatine and myoinositol concentrations, and in the myoinositol/N-acetyl-aspartate ratio. The combination of the variables 'number of dipoles during the late portion of the evoked magnetic field' and 'myoinositol/N-acetyl-aspartate ratio' accounted for 65% of the variance of the Mini Mental State Examination scores.

CONCLUSIONS

These results highlight the importance of assessing the complex brain pathology underlying AD by utilizing multiple brain examination modalities in a coordinate approach.

Proton magnetic resonance spectroscopy and magnetoencephalographic estimation of delta dipole density: a combination of techniques that may contribute to the diagnosis of Alzheimer's disease

Whole-head magnetoencephalographic recordings were obtained from 10 patients with Alzheimer's disease (AD) and 10 healthy controls in a resting position. Spectroscopic examinations were performed by means of a 1.5-tesla whole-body scanner in the temporoparietal regions of both hemispheres. The relationship between (1)H-MRS-based and magnetoencephalography (MEG)-based measures and their conjoined capability to improve the diagnosis of AD were investigated in this study. Logistic regression analyses were performed. Three separated logistic models were calculated for (1)H-MRS-based metabolites, low-frequency magnetic activity, and the combination of both measures. A combined myoinositol/N-acetyl aspartate (mI/NAA)-delta dipole density (DD) model predicted the diagnosis with 90% sensitivity and 100% specificity. Additionally, the combination of temporoparietal mI/NAA and delta DD values explained the variability of individuals' cognitive status. The results support the notion that a multidisciplinary approach may improve the understanding and diagnosis of AD.

Time-modulated enhancing of the fronto-parietal circuits in the very-old elders

Several studies have shown that memory circuits can be reorganised as a function of age. Brain magnetic activity evoked by a memory task was recorded in 19 healthy elderly subjects divided into two groups, a young-elder group (mean age of 62) and senior-elder group (mean age of 76). The young-elder group showed greater activity over the left medial temporal lobe in the late latency windows (between 400 and 800 ms) than the senior-elder group. The senior-elder group showed an initial increased activity (between 150 and 400 ms) over the complex of motor areas, followed by an increased activity in the left temporo-parietal cortex at the late latency window. These results revealed a reorganization of brain networks supporting memory in the eldest subjects. Furthermore, these circuits are reorganised in a time-dependent manner, meaning the rehearsal articulatory process active in the early time window followed by a phonological storage and recognition process in the late latency window.

Correlations of hippocampal atrophy and focal low-frequency magnetic activity in Alzheimer disease: volumetric MR imaging-magnetoencephalographic study

BACKGROUND AND PURPOSE

Patients with Alzheimer disease (AD) have more low-frequency activity on conventional EEG and increased focal magnetoencephalographic (MEG) dipole density (DD) in delta and theta bands. This activity concurs with atrophy and reduced metabolic and perfusion rates, particularly in temporoparietal structures. The relationship between functional and structural measures and their conjoined capability to improve the diagnosis of AD were assessed in this study.

METHODS

Whole-head MEG recordings were obtained in 15 patients in whom the diagnosis of AD had been made and in 16 healthy control subjects during a resting condition. MR imaging volumetric data were also obtained; these included global cerebral, temporal lobe, and hippocampal volumes.

RESULTS

DD in the delta and theta bands was enhanced in the AD group compared with the healthy control subjects. Slow-wave activity differed significantly between the groups in the temporoparietal regions of both hemispheres. Left hippocampal volume was correlated with left temporal and parietal delta DD and left temporal theta DD. A combination of left hippocampal volume and left temporal theta DD enabled correct classification in 87.1% of the patients with AD or control subjects.

CONCLUSION

Results support the predominant role of temporoparietal hypofunction as defined by DD and hippocampal structural deficits shown on MR images in patients with AD. A multidisciplinary perspective of different techniques may improve our understanding of the disease and our diagnostic abilities.

Do cognitive patterns of brain magnetic activity correlate with hippocampal atrophy in Alzheimer's disease?

BACKGROUND

Many reports support the clinical validity of volumetric MRI measurements in Alzheimer's disease.

OBJECTIVE

To integrate functional brain imaging data derived from magnetoencephalography (MEG) and volumetric data in patients with Alzheimer's disease and in age matched controls.

METHODS

MEG data were obtained in the context of a probe-letter memory task. Volumetric measurements were obtained for lateral and mesial temporal lobe regions.

RESULTS

As expected, Alzheimer's disease patients showed greater hippocampal atrophy than controls bilaterally. MEG derived indices of the degree of activation in left parietal and temporal lobe areas, occurring after 400 ms from stimulus onset, correlated significantly with the relative volume of lateral and mesial temporal regions. In addition, the size of the right hippocampus accounted for a significant portion of the variance in cognitive scores independently of brain activity measures.

CONCLUSIONS

These data support the view that there is a relation between hippocampal atrophy and the degree of neurophysiological activity in the left temporal lobe.

Spatio-temporal patterns of brain magnetic activity during a memory task in Alzheimer's disease

The brain magnetic activity patterns in a high load probe-letter (targets and distractors) memory task were examined in patients with Alzheimers's disease (AD) and elderly controls. Control subjects showed a higher number of activity sources over the temporal and parietal cortex between 400 and 700 ms after stimulus onset. However, AD patients showed a higher number of sources over the frontal motor areas, including Broca's and the insula. The number of activity sources on the left parietal areas in response to the target stimuli predicted the AD score oncognitive (MMSE, CAMCOG) and functional staging (FAST) scales. These results suggest that a high information load reveals a deficient functioning of phonological store and reduced task-related activity in temporal and parietal areas, manifesting in a rapid information trace decay. The increased levels of activity in motor areas may reflect a compensatory strategy in an attempt to facilitate rehearsal speed.